Restaurant Recommendation System Research Articles

Comparison of User Based and Item Based Collaborative Filtering in Restaurant Recommendation System

Comparison of User Based and Item Based Collaborative Filtering in Restaurant Recommendation System

Developing a restaurant recommended system via the Vietnamese food image classification

A recommendation system is a system that recommends products and services to users based on daily online searching habits. The recommender system is applied in many fields such as job searching, health care, education, music, and tourism. However, few studies have combined computer vision and collaborative filtering to build a restaurant recommendation system in the tourism sector. In this study, we presented a solution to build a restaurant recommendation system through Vietnamese food image classification. First, we used ResNet-34 which is a variant of the convolutional neural network to classify Vietnamese food images. Then, the system applied the alternative least square technique in matrix factorization and Apache Spark in distributed computing to train the restaurant location dataset. The output was the most relevant restaurant places list to show many choices to users. The experimental datasets included the Vietnamese image and the restaurant location datasets that were collected from kaggle.com and foody.vn websites. For image classification task evaluation, we compared ResNet-34 to variants of ResNet. For the restaurant recommendation task evaluation, we compared alternative least squares with k-nearest neighbor. The comparison results show that the proposed solution is better than traditional popular models.

Popularity-based and Collaborative Filtering Based Restaurant Recommender System

The creation of a Popularity-based and Collaborative Filtering Based Restaurant Recommendation System is the main focus of this project, which is an important application in the fields of recommendation systems and machine learning. The system uses the different python libraries like scikit-learn, pandas, NumPy, Linear Regression, Hashlib and Matplotlib as well as technologies like Python and the Flask Framework, to recommend the restaurants to the users based on the ratings out of 5 and their tastes. With features including user registration, login, restaurant browsing, and recommendation, the suggested system is a user-centric program. The system offers a smooth user experience by combining backend Python frameworks with frontend technologies like HTML, CSS, and Bootstrap. A thorough analysis of the literature made it clear that recommendation systems are essential for improving user pleasure and experience across a range of industries. But my cutting-edge restaurant suggestion system offers a fresh approach. My solution combines cutting-edge machine learning algorithms with intelligent analysis of customer preferences to deliver customized restaurant recommendations. My system uses collaborative and popularity-based filtering algorithms to make sure that users receive recommendations based on their interests and preferences. Through the integration of data from many sources, such as restaurant attributes and user ratings, My system generates precise and pertinent recommendations that boost user engagement and pleasure. Furthermore, My platform offers a user-friendly experience with little additional infrastructure requirements by seamlessly integrating with current websites and applications. My goal is to revolutionize the restaurant discovery process and improve the eating experience for people globally by promoting the widespread adoption of My technology through smart relationships with industry players.

Web Crawling Tripadvisor to Develop a Restaurant Recommendation System for Los Angeles

The widespread use of online review websites has revolutionized how consumers choose restaurants, particularly in popular tourist destinations like Los Angeles, where a vast range of dining options is readily available. However, the sheer abundance of similar cuisine offerings can be overwhelming. To address this challenge, this study used Python Selenium to web crawl Tripadvisor for gathering data about Los Angeles restaurants. Relevant information from user reviews was extracted and analyzed utilizing natural language processing techniques to classify restaurants based on cuisine, price, and customer reviews and ratings. This classification allowed for the identification of distinct dining preferences, providing insights into restaurant selection in tourist-heavy areas. With the application of cosine similarity, the analysis further led to the development of a recommendation system specific to consumers’ needs and preferences. This study thus offers a new approach to improving restaurant discovery and decision-making in busy urban centers in Los Angeles.

Aspect Category Detection of Mobile Edge Customer Reviews: A Distributed and Trustworthy Restaurant Recommendation System

Aspect Category Detection of Mobile Edge Customer Reviews: A Distributed and Trustworthy Restaurant Recommendation System

Restaurant Recommendations Through Natural Language Processing Based on User Rating

This research paper presents a comprehensive study on the development and implementation of a novel Restaurant Recommendation System (RRS) leveraging machine learning techniques and geographical data. The system integrates user preferences, location information, and historical restaurant data to offer personalized recommendations. our research endeavours to contribute to the domain of personalized restaurant recommendation systems. We propose a comprehensive system that amalgamates machine learning techniques, geographical analysis, and a user-friendly graphical interface to offer tailored dining suggestions to users in urban settings. Our approach integrates data pre-processing techniques to handle duplicate entries and encodes categorical variables for enhanced model interpretability. The predictive model, a linear regression algorithm, strives to estimate restaurant prices based on features such as cuisine type, location, and dish category. Geocoding is employed to calculate distances between user-specified locations and recommend establishments within a user-defined radius. The system leverages a Random Forest Classifier to enhance the classification of dish categories, contributing to more precise recommendations. Our system not only predicts restaurant prices but also identifies the most popular establishments based on user-defined parameters. By combining predictive modeling, geographical analysis, and classification algorithms, we aim to create a robust restaurant recommendation system that aligns with the evolving expectations of modern consumers.

Designing an Efficient Restaurant Recommendation System Based on Customer Review Comments by Augmenting Hybrid Filtering Techniques

Designing an Efficient Restaurant Recommendation System Based on Customer Review Comments by Augmenting Hybrid Filtering Techniques

All-in-one picture: visual summary of items in a recommender system

Navigation through large volumes of images is a complex and tedious task that requires tools to facilitate the exploration and discovery of visual information. Photo summaries are one of these tools, which consist of selecting a reduced set of images that best represent the original data source. However, creating photo summaries in the context of recommender systems poses several challenges: How to select the most relevant images for each item? How to encode each image? How to evaluate the quality of the generated summary? In this manuscript, we propose a clustering-based method to create a visual summary in the context of a restaurant recommender system, which includes the photos taken by users who visited the restaurants (items) in a given city. These photos are encoded using a deep neural network that takes into account not only their content but also the relationships between users and restaurants. This encoding will allow us to create a visual summary that captures the essence of user tastes and illustrates the gastronomic offer of the city. We also propose a similarity measure between items based on the users who have visited them and an evaluation method that calculates to what extent the summary obtained represents the original data source. The experimentation carried out includes five datasets and the obtained results demonstrate the adequacy of our proposal for the construction of these summaries.

레스토랑 카테고리와 온라인 소비자 리뷰를 이용한 딥러닝 기반 레스토랑 추천 시스템 개발

최근에는 외식 산업의 발달과 레스토랑 수요의 증가로 인해 레스토랑 추천 시스템 연구가 활발하게 제안되고 있다. 기존 레스토랑 추천 시스템 연구는 정량적인 평점 정보 또는 온라인 리뷰의 감성분석을 통해 소비자의 선호도 정보를 추출하였는데 이는 소비자의 의미론적 선호도 정보는 반영하지 못한다는 한계가 존재한다. 또한, 레스토랑이 포함하는 세부적인 속성을 반영한 추천 시스템 연구는 부족한 실정이다. 이를 해결하기 위해 본 연구에서는 소비자의 선호도와 레스토랑 속성 간의 상호작용을 효과적으로 학습할 수 있는 딥러닝 기반 모델을 제안하였다. 먼저, 합성곱 신경망을 온라인 리뷰에 적용하여 소비자의 의미론적 선호도 정보를 추출했고, 레스토랑 정보에 임베딩 기법을 적용하여 레스토랑의 세부적인 속성을 추출했다. 최종적으로 요소별 연산을 통해 소비자 선호도와 레스토랑 속성 간의 상호작용을 학습하여 소비자의 선호도 평점을 예측했다. 본 연구에서 제안한 모델의 추천 성능을 평가하기 위해 Yelp.com의 온라인 리뷰를 사용한 실험 결과, 기존 연구의 다양한 모델과 비교했을 때 본 연구의 제안 모델이 우수한 추천 성능을 보이는 것을 확인하였다. 본 연구는 레스토랑 산업의 빅데이터를 활용한 맞춤형 레스토랑 추천 시스템을 제안함으로써 레스토랑 연구 분야와 온라인 서비스 제공자에게 학술적 및 실무적 측면에서 다양한 시사점을 제공할 수 있을 것으로 기대한다.

The The Efficiency of Hybridised Genetic Algorithm and Ant Colony Optimisation (HGA-ACO) in a Restaurant Recommendation System

A recommendation system (RS) is used to provide recommendations to users by filtering items based on given inputs. Metaheuristic algorithms such as Genetic Algorithm (GA) and Ant Colony Optimisation (ACO) are known to be used in many RS to provide optimal and good recommendations. Both algorithms are designed based on nature-inspired events, where GA is designed based on the natural evolution process while ACO is based on ants’ behaviour in their natural habit. In this paper, both GA and ACO algorithms were implemented in a restaurant RS and evaluated by using the restaurant’s attributes, which was then followed by a list of recommended restaurants as the output. With the highest score of 99.64% of accuracy, GA overtakes ACO in terms of recommendation accuracy while ACO computed 67.12% lesser runtime than GA. Considering the results acquired, a new hybrid framework known as the HGA-ACO algorithm was proposed. The proposed HGA-ACO has a recommendation accuracy of 99.57% and achieved a 31.37% runtime reduction from GA. Thus, the proposed framework was observed to have improved the output accuracy of ACO and improved the processing time in GA, thus, improving the overall efficiency of the RS.

RESTAURANT RECOMMENDATION SYSTEM

A recommendation system is a collection of algorithms that learn from data and, after processing, can make recommendations to clients. Because of their application in a variety of fields, recommendation systems have recently gained a lot of attraction. Recommender systems are commonly used to forecast user preferences for objects, and they are popular for assisting users in finding restaurants and other products. The Restaurant Recommendation System's main goal is to recommend the best restaurant in the area, as well as food, based on the user's tastes. This programme considers the users' culinary tastes and ratings while making food recommendations.

Constructing a Culinary Tourism Recommendation System Based in Palembang, Indonesian Using Weighted Product Method

Based on the survey that conducted on 33 respondents from the Palembang peoples and non-Palembang peoples, got the result that state, most respondents state they had trouble to deciding which restaurant to go to when visiting Palembang and most respondents need 20 to 60 minutes to determine which restaurant that they want to order the food in Palembang area. Therefore, this study will construct a restaurant recommendation system based on the Palembang region and implementing the Weighted Product method and also adding window maps features. This study aims to assist Palembang and non-Palembang users to choosing system-recommended restaurants in Palembang. The result of this study shows that the recommendation system has successful outcomes in helping the users with great overall feedback showing a high satisfaction level of 89.93%.

RESTAURANT RECOMMENDER SYSTEM USING ITEM BASED COLLABORATIVE FILTERING AND ADJUSTED COSINE ALGORITHM SIMILARITY

In 2018, the Ministry of Industry (Kemenperin) stated that the food and beverage sector contributed 6.34% of the national gross domestic product (GDP). Currently, culinary information can be easily found, both in print and online. The amount of information available sometimes makes people over-informed, making it difficult to choose a restaurant based on their preferences. To assist consumers in selecting a restaurant, we need a system that can provide several recommendations. This study aims to implement the item-based Collaborative Filtering method using the Adjusted Cosine Similarity algorithm on a restaurant recommendation system. The test was carried out with 40 samples from UIN Syarif Hidayatullah Jakarta using purposive sampling because the sample was selected based on specific criteria, and 40 respondents can be said to be correct because of the minimum number of respondents is 30. The accuracy test uses precision, and the determination of the error value uses MAE. The analysis of the research results used three scenarios, which are 5, 20, and 40 users. The third scenario produces the best precision and MAE values. Precision is better if the precision value is close to 1, and MAE is getting better if the MAE value is getting closer to 0. So it can be concluded that the Item-Based method with the Adjusted Cosine algorithm has the best accuracy and error values when the number of users grows.

Restaurant recommender system based on sentiment analysis

Today, exploiting sentiment analysis has become popular in designing recommender systems in various fields, including the restaurant and food area. However, most of the sentiment analysis-based restaurant recommender systems only use static information such as food quality, price, and service quality. The analysis of users’ opinions and the extraction of their food preferences lead to the provision of personalized recommendations, which is a research gap in literature; In this paper, a context-aware recommender system is proposed that extracts the food preferences of individuals from their comments and suggests restaurants in accordance with these preferences. For this purpose, the semantic approach is used to cluster the name of foods extracted from users’ comments and analyze their sentiments about them. Finally, nearby open restaurants are recommended based on their similarity to user preferences. For evaluation, the TripAdvisor website has been used and comments from 100 different users have been collected during the first 9 months of 2018. The precision, recall and f-measure of the system are measured in three scenarios of top1, top3, and top5. The results indicate that the proposed system can provide recommendations with a precision of 92.8%, giving users a high degree of precision. Besides, the system outperforms the previous research in these criteria.

Restaurant Recommendation System Based on User Ratings with Collaborative Filtering

Recommendation systems are widely used as a reference in marketing products or businesses. The number of choices given sometimes makes a person confused in making choices. The recommendation system provides a solution in overcoming this. Collaborative filtering is a fairly popular algorithm used in recommendation systems that are based on references and information obtained from users. User rating is a variable that is widely used as a reference in establishing a recommendation system. User rating can influence other users in making their choice of the same product. The purpose of this study is to conduct an experiment in the application of a collaborative filtering algorithm and use the Pearson correlation function as a method used to see the level of user similarity in making a restaurant recommendation system. The methods used in this research are: (1) datasets preparation, (2) datasets filtering, (3) collaborative filtering, (4) pearson correlation, (5) recommendations, and (6) evaluation. Collaborative filtering combined with the Pearson correlation produces recommendations that are suitable for users based on characteristics or the same level of interest between users, making it easier for users to make choices. This is also indicated by a small error rate based on the RMSE results.

Implementation of a Personalized Restaurant Recommendation System for The Mobility Handicapped

Implementation of a Personalized Restaurant Recommendation System for The Mobility Handicapped

Study on Implementation of Restaurant Recommendation System based on Deep Learning-based Consumer Data

Study on Implementation of Restaurant Recommendation System based on Deep Learning-based Consumer Data

머신러닝 기반 음식점 추천시스템 설계 및 구현

최근 식습관 변화와 인터넷의 발전으로 앱 기반 음식주문 서비스가 생겨났고 이에 따라 배달 시장이 커지고 있다. 또한 사용자는 자신이 선호하는 대상을 쉽게 찾길 원하기 때문에 다양한 분야에 추천 시스템이 도입되고 있다. 추천시스템은 다양한 속성을 포함한 충분한 데이터가 확보되어야 안정적이며 신뢰적인 성능을 보인다. 따라서 본 논문에서는 다양한 목적 및 상황에 맞는 추천을 제공하기 위해 데이터 속성 확장 메커니즘과 머신러닝 기반 음식점 추천시스템을 제안한다. 제안하는 시스템은 추천 리스트 생성을 위해 자연어 평가 기반 음식점 특징 추출 기법, K-means 기반 평가점수 유사그룹 생성기법, 선형회귀 기반 주문량 예측 기법을 제공한다. 본 논문은 Python을 기반으로 제안하는 시스템을 구현하였으며 중국 광저우 지역의 음식점 평가 데이터를 기반으로 추천목록 생성 실험을 수행하였다. 제안하는 시스템은 동적인 특징 추출로 대상의 특성을 유연하게 반영할 수 있으며, 보다 상세한 사용자의 취향 구분이 가능하다. 또한 주문량 예측결과 20% 미만의 오차를 보여 추세파악이 가능할 것으로 생각된다.

Rancang Bangun Sistem Rekomendasi Restoran Menggunakan Metode AHP dan VIKOR pada Platform LINE

Since 2012 until 2017, culinary business in Indonesia has increased by an average 7% to 14% per year. Nowadays, application technology such as Zomato, helps consumers to find information about restaurant’s promos, advantages and disadvantages of a restaurant, and variations of the menu their provided. People who owned the culinary business can interact directly with consumers through social media such as LINE. LINE has 90 million users that communicate with each other by using features that LINE’s provided, such as stickers, news portals, voice and video calls, and LINE Message API service. With 90 million LINE’s users in Indonesia and growing culinary business, developing a restaurant recommendation system in LINE will provide solutions to many people, which inspired the author to develop this system. Data of restaurant it’s taken using Zomato API. Developing this system needs a method of AHP (Analytic Hierarchy Process) and VIKOR (VIsektriterijumsko KOmpromisno Rangiranje), where the application will be built using PHP language. The AHP method is used to assign a weighting value to criteria, and the VIKOR method is used to sort the best alternative option. Based on research through questionnaires, this system’s design and implementation has reached 71,13 value of usability, which mean that system is useful to help people to find restaurant their looking for.
 Index Terms - Culinary, Zomato API, LINE Message API, AHP, VIKOR

Exploring New Vista of intelligent collaborative filtering: A restaurant recommendation paradigm

Due to a busy schedule, people highly dependent on various kinds of online recommendations to utilize their precious time. The collaborative filtering is wide as the recommendation tool in the majority of the commercial recommenders. However, the outcome of collaborative filtering is often jeopardized by the sparsity, cold start, and grey sheep problems. To solve these issues in a more efficient way, a novel collaborative filtering algorithm entitled as Altered Client-based Collaborative Filtering (ACCF) for group recommendation is proposed. ACCF employs Dragonfly Algorithm to deal with the sparsity and neighbor selection. Restaurant recommendation system is utilized as a test bed for the validation of ACCF. With the end goal of performance assessment, a comparative study has been incorporated that depicts the proposed algorithm successfully minimizes the sparsity problem. The experimental outcome rendering ACCF provides 37%, 59%, 53% more Coverage, Precision and F-Measure than the user-based collaborative filtering even applicable for a small sample of data.